Introduction

spend less time cropping cropping is a tedious, time consuming, and error prone task in many heritage digitization workflows a third or more of total production time is manual cropping ai crop aims to drastically reduce the time users spend cropping the ai model behind the tool the term "ai" gets superfluously appended to all sorts of tools nowadays but in this case it is specifically and meaningfully true ai crop really is using ai legacy automatic cropping tools use computer vision (i e shape finding) that struggles with low contrast, soft edges, unusually shaped materials, distracting elements in the frame (e g a bone pick or hand in the corner), or material that has shapes inside of shapes (e g a matted photographic print) ai crop in dt nexus is not using these legacy shape finding technology instead, we have trained an artificial intelligence model from the ground up using tens of thousands of real world images from partner institutions (for whom we are super grateful!) such as the us library of congress, university of western australia, the national library of sweden, and the swiss national library we diligently labeled the components found in all of these images; for example, the page, the page fanning, the gutter, the partial cover, and the target this allows the ai model underpinning ai crop to understand the material inside of the frame it's not seeing a rectangle; it's seeing a page, or a cover, or a target this makes it far more resilient and all around "smarter" than legacy cropping methods the ai crop & straighten feature is now in alpha! while still under development, it offers a preview of ai driven cropping and straightening for material types docid 6jol mj7mtm2bexewsoxu a major update is planned for q2 2025, bringing improved accuracy and performance in the meantime, please sharing images with dt docid 6yfcofsmxk4gawy6 wgdg and feedback to help us refine it note ai crop & straighten (alpha) is an early release and is not production ready